Snapshots on HEAD

As some of you may have noticed there have been no snapshots on HEAD for
about a week now. I'll stick my hand up for causing it. But in a good way.

I've added a dependency on snapshots so they only generate when the
TestBed gives the code a clean bill of health.

This has brought to view several assertions which have been occurring in
the IO and IP layers. I'd like to add this test layer to 3.1 also, which
presently shows the errors but doesn't stop snapshots. The current issues
need to be resolved first.

I've spent some time this week trying to find fixes without much luck.
It's open season on them if anyone can figure it out.

The issues I'm aware of so far are:

 * errors in DiskIO when no module is available (NULL result from 'smart'
module location).

 * unknown segfault in testUfs handling. possibly due to the above.

 * FreeBSD-specific failure to set (ss|sin)_len on generated sockaddr_*

Amos
Received on Fri Nov 14 2008 - 03:22:48 MST